Active appearance models
We demonstrate a novel method of interpreting images using an Active Appearance Model (AAM). An AAM contains a statistical model of the shape and grey-level appearance of the object of interest which can generalise to almost any valid example. During a training phase we learn the relationship between model parameter displacements and the residual errors induced between a training image and a synthesised model example. To match to an image we measure the current residuals and use the model to predict changes to the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and give results of quantitative performance tests. We anticipate that the AAM algorithm will be an important method for locating deformable objects in many applications.
Unable to display preview. Download preview PDF.
- 2.M. J. Black and Y. Yacoob. Recognizing facial expressions under rigid and nonrigid facial motions. In 1st International Workshop on Automatic Face and Gesture Recognition 1995, pages 12–17, Zurich, 1995.Google Scholar
- 3.G. E. Christensen, R. D. Rabbitt, M. I. Miller, S. C. Joshi, U. Grenander, T. A. Coogan, and D. C. V. Essen. Topological Properties of Smooth Anatomic Maps, pages 101–112. Kluwer Academic Publishers, 1995.Google Scholar
- 5.T. Cootes and C. Taylor. Modelling object appearance using the grey-level surface. In E. Hancock, editor, 5th British Machine Vison Conference, pages 479–488, York, England, September 1994. BMVA Press.Google Scholar
- 7.M. Covell. Eigen-points: Control-point location using principal component analysis. In 2nd International Conference on Automatic Face and Gesture Recognition 1997, pages 122–127, Killington, USA, 1996.Google Scholar
- 8.G. J. Edwards, C. J. Taylor, and T. Cootes. Learning to identify and track faces in image sequences. In 8th British Machine Vison Conference, Colchester, UK, 1997.Google Scholar
- 9.G. J. Edwards, C. J. Taylor, and T. Cootes. Face recognition using the active appearance model. In 5th European Conference on Computer Vision, 1998.Google Scholar
- 10.T. Ezzat and T. Poggio. Facial analysis and synthesis using image-based models. In 2nd International Conference on Automatic Face and Gesture Recognition 1997, pages 116–121, Killington, Vermont, 1996.Google Scholar
- 11.U. Grenander and M. Miller. Representations of knowledge in complex systems. Journal of the Royal Statistical Society B, 56:249–603, 1993.Google Scholar
- 12.M. J. Jones and T. Poggio. Multidimensional morphable models. In 6th International Conference on Computer Vision, pages 683–688, 1998.Google Scholar
- 15.B. Moghaddam and A. Pentland. Probabilistic visual learning for object recognition. In 5th International Conference on Computer Vision, pages 786–793, Cambridge, USA, 1995.Google Scholar
- 16.C. Nastar, B. Moghaddam, and A. Pentland. Generalized image matching: Statistical learning of physically-based deformations. In 4th European Conference on Computer Vision, volume 1, pages 589–598, Cambridge, UK, 1996.Google Scholar
- 17.W. Press, S. Teukolsky, W. Vetterling, and B. Flannery. Numerical Recipes in C (2nd Edition). Cambridge University Press, 1992.Google Scholar
- 18.S. Sclaroff and J. Isidoro. Active blobs. In 6th International Conference on Computer Vision, pages 1146–53, 1998.Google Scholar